Noometry

Model comparison

Qwen2-72B vs Qwen3-Coder 480B-A35B Instruct

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 30.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Qwen3-Coder 480B-A35B Instruct Alibaba (Qwen)

38.1

Rank #190 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3-Coder 480B-A35B Instruct leads 37.0 to 21.2.
  • The biggest single-benchmark swing is WeirdML: 11.3% for Qwen2-72B and 41.2% for Qwen3-Coder 480B-A35B Instruct.

Side by side

Qwen2-72BQwen3-Coder 480B-A35B Instruct
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.038.1
Released2024-06-072025-04
WeightsOpenOpen
Context window—262K
Max output—66K
Input $ / M tokens—$1.50
Output $ / M tokens—$7.50
Results tracked2625

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 29.1 (#310), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
WeirdML11.3%41.2%
LMArena Coding11961412
SWE-bench Verified (bash only)—55.4%
LMArena WebDev—1275
GSO—4.9%
BigCodeBench Instruct38.5%—
BigCodeBench Complete54%—
ALE-Bench—461.45
AlgoTune—1.44

Agentic & Tool Use Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 17.0 (#146), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
Terminal-Bench—27.2%
TheAgentCompany1.1%—
METR Time Horizons29.9%—

Reasoning Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 23.2 (#181), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Hard Prompts11911372
Kagi LLM Benchmark—49.5%
Epoch Capabilities Index125.28—

Math Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 30.2 (#236), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Math12351365
MATH Level 539.1%—

Knowledge Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 21.2 (#275), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Expert11711338
GPQA Diamond40.8%—
MMLU82.4%—

Multilingual Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 35.9 (#244), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Non-English11761346
LMArena Chinese12401357
LMArena French11701398
LMArena German11511325
LMArena Japanese11111310
LMArena Korean10831305
LMArena Russian11691366
LMArena Spanish11691360

Instruction Following Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 61.7 (#241), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Instruction Following11811355

Long Context Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 36.1 (#235), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Longer Query11921378

Writing & Preference Qwen3-Coder 480B-A35B Instruct leads

Qwen2-72B: 40.8 (#241), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

BenchmarkQwen2-72BQwen3-Coder 480B-A35B Instruct
LMArena Text12031357
LMArena Creative Writing11811333
LMArena Multi-Turn11961365

Frequently asked questions

Is Qwen2-72B better than Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 30.0 on the Noometry Index.

Is Qwen2-72B or Qwen3-Coder 480B-A35B Instruct better for coding?

Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 29.1 in the Noometry coding category.

How many benchmarks do Qwen2-72B and Qwen3-Coder 480B-A35B Instruct share?

18 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.

Related comparisons

Go deeper